Considerations for Predictive Modeling in Insurance Applications

Considerations for Predictive Modeling in Insurance Applications

Considerations for Predictive Modeling in Insurance Applications May 2019 2 Considerations for Predictive Modeling in Insurance Applications AUTHORS Eileen Burns, FSA, MAAA SPONSORS Modeling Section Gene Dan, FCAS, MAAA, CSPA Predictive Analytics and Futurism Anders Larson, FSA, MAAA Section Bob Meyer, FCAS, MAAA Committee on Life Insurance Research Zohair Motiwalla, FSA, MAAA Product Development Section Guy Yollin Reinsurance Section Milliman Caveat and Disclaimer The opinions expressed and conclusions reached by the authors are their own and do not represent any official position or opinion of the Society of Actuaries or its members. The Society of Actuaries makes no representation or warranty to the accuracy of the information Copyright © 2019 by the Society of Actuaries. All rights reserved. Copyright © 2019 Society of Actuaries 3 CONTENTS Acknowledgments .................................................................................................................................................... 5 Section 1: Introduction ............................................................................................................................................. 6 Section 2: Literature Review ..................................................................................................................................... 8 2.1 BACKGROUND ...................................................................................................................................................... 8 2.2 PROJECT OBJECTIVE ............................................................................................................................................ 9 2.3 DATA ACQUISITION AND PREPARATION .......................................................................................................... 10 2.4 ALGORITHM SELECTION .................................................................................................................................... 12 2.5 FEATURE ENGINEERING AND SELECTION ........................................................................................................ 14 2.6 MODEL EVALUATION AND MEASURES OF SUCCESS ....................................................................................... 16 2.7 MODEL DEPLOYMENT ....................................................................................................................................... 18 2.8 MODEL GOVERNANCE ....................................................................................................................................... 19 2.9 SOFTWARE SELECTION ...................................................................................................................................... 21 Section 3: Predictive Analytics Considerations ........................................................................................................ 25 3.1 PROJECT OBJECTIVE .......................................................................................................................................... 25 3.2 DATA ACQUISITION AND PREPARATION .......................................................................................................... 26 3.3 ALGORITHM SELECTION .................................................................................................................................... 28 3.4 FEATURE ENGINEERING AND SELECTION ........................................................................................................ 28 3.5 MODEL EVALUATION AND MEASURES OF SUCCESS ....................................................................................... 30 3.6 MODEL DEPLOYMENT ....................................................................................................................................... 31 3.7 MODEL GOVERNANCE ....................................................................................................................................... 32 3.8 SOFTWARE SELECTION ...................................................................................................................................... 34 3.9 STAYING CURRENT ............................................................................................................................................ 35 Section 4: Case Study .............................................................................................................................................. 37 4.1 CASE STUDY BACKGROUND .............................................................................................................................. 37 4.2 PROJECT OBJECTIVE .......................................................................................................................................... 38 4.2.1 COMMENTARY ....................................................................................................................................... 39 4.3 DATA ACQUISITION AND PREPARATION .......................................................................................................... 39 4.3.1 DATA SOURCES ....................................................................................................................................... 39 4.3.2 DATA RECONCILIATION .......................................................................................................................... 40 4.3.3 COMMENTARY ....................................................................................................................................... 40 4.4 ALGORITHM SELECTION .................................................................................................................................... 40 4.4.1 CANDIDATE ALGORITHMS ..................................................................................................................... 40 4.4.2 CONCEPTUAL DESIGN AND ALGORITHM SELECTION ........................................................................... 41 4.4.3 COMMENTARY ....................................................................................................................................... 43 4.5 SOFTWARE SELECTION ...................................................................................................................................... 43 4.5.1 PROJECT STRUCTURE ............................................................................................................................. 44 4.5.2 COMMENTARY ....................................................................................................................................... 46 4.6 FEATURE ENGINEERING AND SELECTION ........................................................................................................ 46 4.6.1 COMMENTARY ....................................................................................................................................... 50 4.7 MODEL EVALUATION AND MEASURES OF SUCCESS ....................................................................................... 50 4.7.1 ACTUAL VERSUS EXPECTED ANALYSIS .................................................................................................. 50 4.7.2 PRECISON ................................................................................................................................................ 55 4.7.3 COMMENTARY ....................................................................................................................................... 59 4.8 MODEL DEPLOYMENT ....................................................................................................................................... 60 4.8.1 COMMENTARY ....................................................................................................................................... 61 4.9 MODEL GOVERNANCE ....................................................................................................................................... 61 4.9.1 ORGANIZATIONAL STRUCTURE ............................................................................................................. 61 Copyright © 2019 Society of Actuaries 4 4.9.2 MODEL INVENTORY ............................................................................................................................... 62 4.9.3 VERSION CONTROL PRACTICES ............................................................................................................. 62 4.9.4 INDEPENDENT REVIEW OF MODELS ..................................................................................................... 63 4.9.5 DOCUMENTATION PRACTICES .............................................................................................................. 63 4.9.6 COMMENTARY ....................................................................................................................................... 63 Appendix 1: Survey Results ..................................................................................................................................... 64 DEMOGRAPHICS........................................................................................................................................................... 64 BUSINESS PURPOSE ..................................................................................................................................................... 68 DATA ACQUISITION AND PREPARATION ..................................................................................................................... 71 ALGORITHM SELECTION

View Full Text

Details

  • File Type
    pdf
  • Upload Time
    -
  • Content Languages
    English
  • Upload User
    Anonymous/Not logged-in
  • File Pages
    98 Page
  • File Size
    -

Download

Channel Download Status
Express Download Enable

Copyright

We respect the copyrights and intellectual property rights of all users. All uploaded documents are either original works of the uploader or authorized works of the rightful owners.

  • Not to be reproduced or distributed without explicit permission.
  • Not used for commercial purposes outside of approved use cases.
  • Not used to infringe on the rights of the original creators.
  • If you believe any content infringes your copyright, please contact us immediately.

Support

For help with questions, suggestions, or problems, please contact us